A minimal implementation of DeepMind's Genie world model

GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Getting Started with Xilinx ML Suite

An educational resource to help anyone learn deep reinforcement learning.

Build Graph Nets in Tensorflow

PHP based web index for image displaying

Deep Reinforcement Learning for Keras.

Machine learning on FPGAs using HLS